Intersection vehicle dispatching method, device, equipment and computer-readable storage medium

Abstract

The present application relates to the field of unmanned driving, and provides a vehicle scheduling method, device, equipment and computer-readable storage medium at intersections, so as to reduce computational complexity and enable continuous scheduling. The method includes: when a vehicle entrance and exit is detected at time t, updating the state information of each unmanned vehicle in the dispatched vehicle set Ic according to the vehicle state information received at time t, to obtain the updated dispatched vehicle set Ic'; Get the position vector information of each unmanned vehicle in the update scheduling vehicle set Ic' when it arrives at the intersection in the shortest time; The position vector information is used to obtain the intersection sequence set O; for the unmanned vehicle represented by each element in the intersection sequence set O, the trajectory planning vector U of the unmanned vehicle is obtained c , V c and P c ; Send the acceleration, speed and position that the unmanned vehicle should have when it is at the intersection to the corresponding unmanned vehicle for execution.

Description

technical field [0001] The present invention relates to the field of unmanned driving, in particular to a vehicle dispatching method, device, equipment and computer-readable storage medium at an intersection. Background technique [0002] In the vehicle-road collaborative network, the roadside unit (Road Side Unit, RSU) can send control scheduling instructions to the vehicle according to the vehicle status information, so as to reasonably avoid potential dangers or improve driving efficiency. Coordinated dispatching of vehicles at intersections is a typical application scenario for autonomous driving. The dispatching system is mainly divided into a centralized dispatching system and a distributed dispatching system. The centralized dispatching system includes a central dispatching node (RSU), which is mainly responsible for collecting vehicle information and making decisions. The scheduling performance of the centralized scheduling system depends on the computing power of th...

AI Technical Summary

Problems solved by technology

[0004] However, the solutions of the above-mentioned prior art still have the following defects: 1) each time all vehicles are solved at the same time, the computational complexity increases exponentially with the increase of the number of variables, and it is difficult to cope with the scene when the vehicle density is high in reality; 2) When some vehicles cannot be reasonably scheduled due to their poor state, the global optimization problem has no solution, and the scheduling process will be interrupted

Images